{"list":"other","total":102,"rows":[{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"1803.08669","title":"Pyramid Stereo Matching Network","created":"2018-03-23","cited_by_count":489},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"id":"1703.04309","title":"End-to-End Learning of Geometry and Context for Deep Stereo Regression","created":"2017-03-13","cited_by_count":360},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2109.07547","title":"RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching","created":"2021-09-15","cited_by_count":353},{"id":"2403.12013","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image","created":"2024-03-18","cited_by_count":286},{"id":"2211.05783","title":"Unifying Flow, Stereo and Depth Estimation","created":"2022-11-10","cited_by_count":275},{"id":"1904.06587","title":"GA-Net: Guided Aggregation Net for End-to-end Stereo Matching","created":"2019-04-13","cited_by_count":244},{"id":"1903.04025","title":"Group-wise Correlation Stereo Network","created":"2019-03-10","cited_by_count":235},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204},{"id":"2203.11483","title":"Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation","created":"2022-03-22","cited_by_count":197},{"id":"2011.02910","title":"Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers","created":"2020-11-05","cited_by_count":190},{"id":"2303.06615","title":"Iterative Geometry Encoding Volume for Stereo Matching","created":"2023-03-12","cited_by_count":190},{"id":"2005.06209","title":"On the uncertainty of self-supervised monocular depth estimation","created":"2020-05-13","cited_by_count":182},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"2501.09898","title":"FoundationStereo: Zero-Shot Stereo Matching","created":"2025-01-17","cited_by_count":173},{"id":"2010.13501","title":"Hierarchical Neural Architecture Search for Deep Stereo Matching","created":"2020-10-26","cited_by_count":166},{"id":"2409.18124","title":"Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction","created":"2024-09-26","cited_by_count":166},{"id":"2104.04314","title":"CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching","created":"2021-04-09","cited_by_count":154},{"id":"1510.05970","title":"Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches","created":"2015-10-20","cited_by_count":151},{"id":"1810.02695","title":"Learning Depth with Convolutional Spatial Propagation Network","created":"2018-10-04","cited_by_count":136},{"id":"1909.09051","title":"Self-Supervised Monocular Depth Hints","created":"2019-09-19","cited_by_count":127},{"id":"1912.06704","title":"Hierarchical Deep Stereo Matching on High-resolution Images","created":"2019-12-13","cited_by_count":126},{"id":"1910.02550","title":"ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation","created":"2019-10-06","cited_by_count":124},{"id":"2007.12140","title":"HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching","created":"2020-07-23","cited_by_count":120},{"id":"2104.03866","title":"SMD-Nets: Stereo Mixture Density Networks","created":"2021-04-08","cited_by_count":120},{"id":"2003.13951","title":"Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volume","created":"2020-03-31","cited_by_count":116},{"id":"1909.05845","title":"DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch","created":"2019-09-12","cited_by_count":114},{"id":"2105.14021","title":"Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging","created":"2021-05-28","cited_by_count":104},{"id":"2406.01493","title":"Learning Temporally Consistent Video Depth from Video Diffusion Priors","created":"2024-06-03","cited_by_count":100},{"id":"2003.13948","title":"Segmenting Transparent Objects in the Wild","created":"2020-03-31","cited_by_count":98},{"id":"1812.06264","title":"Hierarchical Discrete Distribution Decomposition for Match Density Estimation","created":"2018-12-15","cited_by_count":93},{"id":"1807.08865","title":"StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction","created":"2018-07-24","cited_by_count":88},{"id":"1807.11699","title":"SegStereo: Exploiting Semantic Information for Disparity Estimation","created":"2018-07-31","cited_by_count":88},{"id":"1810.05424","title":"Real-time self-adaptive deep stereo","created":"2018-10-12","cited_by_count":80},{"id":"1808.06586","title":"Learning Monocular Depth by Distilling Cross-domain Stereo Networks","created":"2018-08-20","cited_by_count":64},{"id":"1904.04144","title":"Learning monocular depth estimation infusing traditional stereo knowledge","created":"2019-04-08","cited_by_count":64},{"id":"1708.09204","title":"Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching","created":"2017-08-30","cited_by_count":63},{"id":"2202.08471","title":"TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baseline","created":"2022-02-17","cited_by_count":55},{"id":"1810.11408","title":"Anytime Stereo Image Depth Estimation on Mobile Devices","created":"2018-10-26","cited_by_count":54},{"id":"2212.10428","title":"HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios","created":"2022-12-20","cited_by_count":53},{"id":"2501.09466","title":"DEFOM-Stereo: Depth Foundation Model Based Stereo Matching","created":"2025-01-16","cited_by_count":52},{"id":"2008.03633","title":"Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes","created":"2020-08-09","cited_by_count":50},{"id":"2206.04671","title":"Open Challenges in Deep Stereo: the Booster Dataset","created":"2022-06-09","cited_by_count":48},{"id":"2412.04472","title":"Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail","created":"2024-12-05","cited_by_count":47},{"id":"2303.17603","title":"NeRF-Supervised Deep Stereo","created":"2023-03-30","cited_by_count":46},{"id":"2312.02284","title":"PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation","created":"2023-12-04","cited_by_count":41},{"id":"2002.12730","title":"Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fields","created":"2020-02-28","cited_by_count":40},{"id":"2404.09790","title":"NTIRE 2024 Challenge on Image Super-Resolution (x4): Methods and Results","created":"2024-04-15","cited_by_count":40},{"id":"2003.14030","title":"Distilled Semantics for Comprehensive Scene Understanding from Videos","created":"2020-03-31","cited_by_count":39},{"id":"2210.11719","title":"Context-Enhanced Stereo Transformer","created":"2022-10-21","cited_by_count":37},{"id":"2307.14071","title":"Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching","created":"2023-07-26","cited_by_count":37},{"id":"2307.15052","title":"Learning Depth Estimation for Transparent and Mirror Surfaces","created":"2023-07-27","cited_by_count":34},{"id":"2301.08245","title":"Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces","created":"2023-01-19","cited_by_count":33},{"id":"1803.05196","title":"EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matching","created":"2018-03-14","cited_by_count":32},{"id":"1810.04093","title":"Geometry meets semantics for semi-supervised monocular depth estimation","created":"2018-10-09","cited_by_count":29},{"id":"1905.07443","title":"AutoDispNet: Improving Disparity Estimation With AutoML","created":"2019-05-17","cited_by_count":29},{"id":"2404.11313","title":"NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results","created":"2024-04-17","cited_by_count":29},{"id":"2407.16698","title":"Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions","created":"2024-07-23","cited_by_count":29},{"id":"2411.19189","title":"Video Depth without Video Models","created":"2024-11-28","cited_by_count":29},{"id":"2303.14840","title":"On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks","created":"2023-03-26","cited_by_count":26},{"id":"2504.10686","title":"The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report","created":"2025-04-14","cited_by_count":26},{"id":"2308.00728","title":"ELFNet: Evidential Local-global Fusion for Stereo Matching","created":"2023-08-01","cited_by_count":25},{"id":"2504.10685","title":"NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results","created":"2025-04-14","cited_by_count":25},{"id":"2101.00431","title":"On the confidence of stereo matching in a deep-learning era: a quantitative evaluation","created":"2021-01-02","cited_by_count":23},{"id":"2407.07816","title":"A Survey on Deep Stereo Matching in the Twenties","created":"2024-07-10","cited_by_count":23},{"id":"2504.12711","title":"NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results","created":"2025-04-17","cited_by_count":22},{"id":"2504.12276","title":"The Tenth NTIRE 2025 Image Denoising Challenge Report","created":"2025-04-16","cited_by_count":21},{"id":"2110.15367","title":"Neural Disparity Refinement for Arbitrary Resolution Stereo","created":"2021-10-28","cited_by_count":20},{"id":"2105.08630","title":"Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report","created":"2021-05-17","cited_by_count":19},{"id":"2501.08643","title":"MonSter++: Unified Stereo Matching, Multi-view Stereo, and Real-time Stereo with Monodepth Priors","created":"2025-01-15","cited_by_count":19},{"id":"2504.12401","title":"NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results","created":"2025-04-16","cited_by_count":16},{"id":"2504.13131","title":"NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results","created":"2025-04-17","cited_by_count":14},{"id":"2505.12089","title":"NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results","created":"2025-05-17","cited_by_count":14},{"id":"2211.12174","title":"The Monocular Depth Estimation Challenge","created":"2022-11-22","cited_by_count":13},{"id":"2309.16019","title":"GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes","created":"2023-09-26","cited_by_count":13},{"id":"2304.07051","title":"The Second Monocular Depth Estimation Challenge","created":"2023-04-14","cited_by_count":12},{"id":"2405.14873","title":"Federated Online Adaptation for Deep Stereo","created":"2024-05-23","cited_by_count":12},{"id":"2504.14582","title":"NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results","created":"2025-04-20","cited_by_count":12},{"id":"2505.03007","title":"NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results","created":"2025-05-05","cited_by_count":12},{"id":"2504.15003","title":"NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: KwaiSR Dataset and Study","created":"2025-04-21","cited_by_count":11},{"id":"2404.16831","title":"The Third Monocular Depth Estimation Challenge","created":"2024-04-25","cited_by_count":10},{"id":"2504.14600","title":"NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results","created":"2025-04-20","cited_by_count":10},{"id":"2505.18988","title":"NTIRE 2025 Challenge on Video Quality Enhancement for Video Conferencing: Datasets, Methods and Results","created":"2025-05-25","cited_by_count":9},{"id":"2506.02197","title":"NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution","created":"2025-06-02","cited_by_count":9},{"id":"2504.17787","title":"The Fourth Monocular Depth Estimation Challenge","created":"2025-04-24","cited_by_count":8},{"id":"2505.16314","title":"NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment","created":"2025-05-22","cited_by_count":8},{"id":"2506.02875","title":"NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results","created":"2025-06-03","cited_by_count":6}],"next_cursor":"100"}